From cec86acdf5ef001319bd9a3da024025d4a337de9 Mon Sep 17 00:00:00 2001
From: Venkat Malladi <venkat.malladi@utsouthwestern.edu>
Date: Sun, 6 Jan 2019 10:56:41 -0600
Subject: [PATCH] Change fastq's to be new sample names as defined by the
sample_id.
---
workflow/main.nf | 4 ++--
workflow/scripts/trim_reads.py | 37 ++++++++++++++++++++++++++++++-
workflow/tests/test_trim_reads.py | 8 +++----
3 files changed, 42 insertions(+), 7 deletions(-)
diff --git a/workflow/main.nf b/workflow/main.nf
index 1103db0..77f22be 100644
--- a/workflow/main.nf
+++ b/workflow/main.nf
@@ -104,12 +104,12 @@ process trimReads {
if (pairedEnd) {
"""
- python3 $baseDir/scripts/trim_reads.py -f ${reads[0]} ${reads[1]} -p
+ python3 $baseDir/scripts/trim_reads.py -f ${reads[0]} ${reads[1]} -s $sampleId -p
"""
}
else {
"""
- python3 $baseDir/scripts/trim_reads.py -f ${reads[0]}
+ python3 $baseDir/scripts/trim_reads.py -f ${reads[0]} -s $sampleId
"""
}
diff --git a/workflow/scripts/trim_reads.py b/workflow/scripts/trim_reads.py
index 036c5f7..75e0b8c 100644
--- a/workflow/scripts/trim_reads.py
+++ b/workflow/scripts/trim_reads.py
@@ -5,6 +5,7 @@
import subprocess
import argparse
import shutil
+import os
import logging
EPILOG = '''
@@ -32,6 +33,10 @@ def get_args():
nargs='+',
required=True)
+ parser.add_argument('-s', '--sample',
+ help="The name of the sample.",
+ required=True)
+
parser.add_argument('-p', '--paired',
help="True/False if paired-end or single end.",
default=False,
@@ -61,6 +66,32 @@ def check_tools():
raise Exception('Missing cutadapt')
+def rename_reads(fastq, sample, paired):
+ '''Rename fastq files by sample name.'''
+
+ # Get current directory to build paths
+ cwd = os.getcwd()
+
+ renamed_fastq = []
+
+ if paired: # paired-end data
+ # Set file names
+ renamed_fastq[0] = cwd + '/' + sample + '_R1.fastq.gz'
+ renamed_fastq[1] = cwd + '/' + sample + '_R2.fastq.gz'
+
+ # Great symbolic links
+ os.symlink(fastq[0], renamed_fastq[0])
+ os.symlink(fastq[1], renamed_fastq[1])
+ else:
+ # Set file names
+ renamed_fastq[0] = cwd + '/' + sample + '_R1.fastq.gz'
+
+ # Great symbolic links
+ os.symlink(fastq[0], renamed_fastq[0])
+
+ return fastq_rename
+
+
def trim_reads(fastq, paired):
'''Run trim_galore on 1 or 2 files.'''
@@ -82,6 +113,7 @@ def trim_reads(fastq, paired):
def main():
args = get_args()
fastq = args.fastq
+ sample = args.sample
paired = args.paired
# Create a file handler
@@ -91,8 +123,11 @@ def main():
# Check if tools are present
check_tools()
+ # Rename fastq files by sample
+ fastq_rename = rename_reads(fastq, sample paired)
+
# Run trim_reads
- trim_reads(fastq, paired)
+ trim_reads(fastq_rename, paired)
if __name__ == '__main__':
diff --git a/workflow/tests/test_trim_reads.py b/workflow/tests/test_trim_reads.py
index b925627..502312f 100644
--- a/workflow/tests/test_trim_reads.py
+++ b/workflow/tests/test_trim_reads.py
@@ -13,9 +13,9 @@ test_output_path = os.path.dirname(os.path.abspath(__file__)) + \
@pytest.mark.singleend
def test_trim_reads_singleend():
raw_fastq = test_data_path + 'ENCFF833BLU.fastq.gz'
- trimmed_fastq = test_output_path + 'ENCFF833BLU_trimmed.fq.gz'
+ trimmed_fastq = test_output_path + 'ENCLB144FDT_trimmed.fq.gz'
trimmed_fastq_report = test_output_path + \
- 'ENCFF833BLU.fastq.gz_trimming_report.txt'
+ 'ENCLB144FDT.fastq.gz_trimming_report.txt'
assert os.path.getsize(raw_fastq) != os.path.getsize(trimmed_fastq)
assert os.path.getsize(trimmed_fastq) == 2512853101
assert 'Trimming mode: single-end' in open(trimmed_fastq_report).readlines()[4]
@@ -24,9 +24,9 @@ def test_trim_reads_singleend():
@pytest.mark.pairedend
def test_trim_reads_pairedend():
raw_fastq = test_data_path + 'ENCFF582IOZ.fastq.gz'
- trimmed_fastq = test_output_path + ' ENCFF582IOZ_val_2.fq.gz'
+ trimmed_fastq = test_output_path + ' ENCLB637LZP_val_2.fq.gz'
trimmed_fastq_report = test_output_path + \
- 'ENCFF582IOZ.fastq.gz_trimming_report.txt'
+ 'ENCLB637LZP.fastq.gz_trimming_report.txt'
assert os.path.getsize(raw_fastq) != os.path.getsize(trimmed_fastq)
assert os.path.getsize(trimmed_fastq) == 2229312710
assert 'Trimming mode: paired-end' in open(trimmed_fastq_report).readlines()[4]
--
GitLab